Data wrangling - Deficit as % of GDP

Note that positive values in deficit_pc mean budget surpluses and negative deficits Uploading data

df_deficit_pct <- read_csv("data/deficit_pct_gdp_OECD.csv")

Creating a wide-form dataset with columns for each year There are 23 rows with flag E (estimate/preliminary data) and 1 B (break in series) that were put in table df_e_or_b

df_deficit_pct %>% count(`Flag Codes`)

## # A tibble: 3 x 2
##   `Flag Codes`     n
##   <chr>        <int>
## 1 B                1
## 2 E               23
## 3 <NA>          1116

df_deficit_pct %>% filter(!is.na(`Flag Codes`))

## # A tibble: 24 x 8
##    LOCATION INDICATOR SUBJECT MEASURE FREQUENCY  TIME deficit_pc `Flag Codes`
##    <chr>    <chr>     <chr>   <chr>   <chr>     <dbl>      <dbl> <chr>       
##  1 FIN      GGNLEND   TOT     PC_GDP  A          1975       4.93 E           
##  2 FIN      GGNLEND   TOT     PC_GDP  A          1976       7.61 E           
##  3 FIN      GGNLEND   TOT     PC_GDP  A          1977       6.25 E           
##  4 FIN      GGNLEND   TOT     PC_GDP  A          1978       3.83 E           
##  5 FIN      GGNLEND   TOT     PC_GDP  A          1979       3.40 E           
##  6 FRA      GGNLEND   TOT     PC_GDP  A          2018      -2.29 E           
##  7 FRA      GGNLEND   TOT     PC_GDP  A          2019      -3.01 E           
##  8 GRC      GGNLEND   TOT     PC_GDP  A          2010     -11.3  B           
##  9 GRC      GGNLEND   TOT     PC_GDP  A          2018       1.02 E           
## 10 GRC      GGNLEND   TOT     PC_GDP  A          2019       1.52 E           
## # … with 14 more rows

df_wide_deficit <- df_deficit_pct %>% 
  select(-`Flag Codes`) %>% #this removes the variable Flag Codes to make the wide dataset cleaner
  pivot_wider(names_from = TIME, values_from = deficit_pc)

Visualising balance as % of GDP for all countries over the years (positive values are surpluses, negative values are deficits)

  p <- df_deficit_pct %>% #making p into a ggplot object to visualise w/ plotly
 # line below would invert surplus/deficit in deficit_pc, making higher values mean higher deficits
 # mutate(deficit_pc=-deficit_pc) %>% 
  ggplot(aes(TIME, deficit_pc, colour=LOCATION)) + 
  geom_line()
  ggplotly(p) #plotly lets me see the legend when scrolling through the plot

Creating rolling averages over 5, 7 and 10 years

  df_deficit_pct <- df_deficit_pct %>% #this function uses longform
  group_by(LOCATION) %>% 
  mutate(bal_05ya = rollmean(deficit_pc, k = 5, fill = NA),
         bal_07ya = rollmean(deficit_pc, k = 7, fill = NA),
         bal_10ya = rollmean(deficit_pc, k = 10, fill = NA)) %>% 
        ungroup() #this closes that group_by(LOCATION)

Visualising 5 year rolling averages of balance as % of GDP for all countries

    p1 <- df_deficit_pct %>%
    ggplot(aes(TIME, bal_05ya, colour=LOCATION)) + 
    geom_line()
    ggplotly(p1)

Visualising 7 year rolling averages of balance as % of GDP for all countries

    p2 <- df_deficit_pct %>%
    ggplot(aes(TIME, bal_07ya, colour=LOCATION)) + 
    geom_line()
    ggplotly(p2)

Visualising 10 year rolling averages of balance as % of GDP for all countries

    p3 <- df_deficit_pct %>%
    ggplot(aes(TIME, bal_10ya, colour=LOCATION)) + 
    geom_line()
    ggplotly(p3) 

Visualising 7 year rolling averages of balance as % of GDP for all countries from 2000

    p4 <- df_deficit_pct %>%
    filter(TIME>=2000) %>% 
    ggplot(aes(TIME, bal_07ya, colour=LOCATION)) + 
    geom_line()
    ggplotly(p4)